Shuiwu/n27_neimenggu.py

#!/usr/bin/env python
# coding:utf-8

import re
import requests,json
from setting import proxies
from urllib import parse
from lxml import etree
from mongo_cho import myco27,r_myco15,myco27_b
from rety import retry
r = requests.session()
r.keep_alive = False

def r1_d(url,dt):
    # url = 'http://neimenggu.chinatax.gov.cn/nsfw/sscx/zdaj/hlbeszdwfaj/202106/t20210609_751387.html'
    headers = {
            "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.85 Safari/537.36",
        }
    response = r.get(url=url,headers=headers,proxies=proxies)
    response.encoding = 'UTF-8'
    html = response.text
    selector = etree.HTML(html)
    a = selector.xpath('//table//tr')
    dict1 = {}
    for i in a:
        k1 = i.xpath('td[1]')
        if k1:
            k2 = k1[0].xpath('string(.)').strip()

            k3 = k2.replace('\r', '').replace('\t', '').replace('\n', '').replace(' ', '')
            # print(k2)
            v1 = i.xpath('td[2]')
            if v1:
                v2 = v1[0].xpath('string(.)').strip()
                v3 = v2.replace('\r', '').replace('\t', '').replace('\n', '').replace(' ', '')
                # print(v3)
            else:
                v3 = ''
            if k3:
                dict1[k3] = v3
    dict1['url'] = url
    dict1['date'] = dt
    print(dict1)
    return dict1

# r1_d('1')


@retry(3)
def r1():
    url = 'http://neimenggu.chinatax.gov.cn/nsfw/sscx/zdaj/sj/2023/'  ##查看时间
    headers = {
        "User-Agent": "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.85 Safari/537.36",
    }
    response = r.get(url=url,headers=headers,proxies=proxies)
    response.encoding = 'UTF-8'
    html = response.text
    # print(html)
    selector = etree.HTML(html)
    a = re.findall('href="(.*?)"',html)
    for i in a:
        # print(i)
        if "html" in i:
            url1 = 'http://neimenggu.chinatax.gov.cn/nsfw/sscx/zdaj' + i.replace('../..','')
            print(url1)
            u1 = url1.split('/')
            u2 = u1[-1].split('_')[0]
            # print(u2)
            dt = u2[1:5] + '/' + u2[5:7] + '/' + u2[7:9]
            print(dt)
            utf = r_myco15.sismember('n27', url1)  ##更改
            if not utf:
                rsd = r1_d(url1, dt)
                myco27.insert_one(rsd)
                myco27_b.insert_one(rsd)
                r_myco15.sadd('n27', url1)
                print('存入主备库，>>>n27')
            else:
                print('已存在，>>>n27')
            # time.sleep(10)

r1()